mlsanityData to 14 Oct 2026

VISION Datasets: A Benchmark for Vision-based InduStrial InspectiON

arXiv 2306.07890 ↗First posted 13 Jun 2023cs.CV cs.LGcited by 25

Not on the map. Why?

Abstract (arXiv)

Despite progress in vision-based inspection algorithms, real-world industrial challenges -- specifically in data availability, quality, and complex production requirements -- often remain under-addressed. We introduce the VISION Datasets, a diverse collection of 14 industrial inspection datasets, uniquely poised to meet these challenges. Unlike previous datasets, VISION brings versatility to defect detection, offering annotation masks across all splits and catering to various detection methodologies. Our datasets also feature instance-segmentation annotation, enabling precise defect identification. With a total of 18k images encompassing 44 defect types, VISION strives to mirror a wide range of real-world production scenarios. By supporting two ongoing challenge competitions on the VISION Datasets, we hope to foster further advancements in vision-based industrial inspection.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). Builds on 19 of its 33 references that are in the map. First posted on arXiv 13 Jun 2023.

Builds on

19 of 33 references.

References · 19

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  2. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  4. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  5. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
  6. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  7. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 691
  8. 2019Hybrid Task Cascade for Instance Segmentationcited by 481
  9. 2019Deep Learning for Anomaly Detection: A Surveycited by 358
  10. 2022Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentationcited by 344
  11. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 223
  12. 2017Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detectioncited by 209
7 more
  1. 2019Segmentation-Based Deep-Learning Approach for Surface-Defect Detectioncited by 145
  2. 2022ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Modelscited by 141
  3. 2021Mixed supervision for surface-defect detection: from weakly to fully supervised learningcited by 101
  4. 2021CBNet: A Composite Backbone Network Architecture for Object Detectioncited by 77
  5. 2022Roboflow 100: A Rich, Multi-Domain Object Detection Benchmarkcited by 26
  6. 2021Self-supervised Semi-supervised Learning for Data Labeling and Quality Evaluationcited by 7
  7. 2022Synthetic Defect Generation for Display Front-of-Screen Quality Inspection: A Surveycited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 9; 2025: 9; 2026: 4.

25 papers.

Sort:

By area:

  1. 2023Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructionscited by 77
  2. 2024GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detectioncited by 42
  3. 2023Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semanticscited by 16
  4. 2024VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detectioncited by 13
  5. 2026Advances in Global Solvers for 3D Visioncited by 13
  6. 2025EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPOcited by 12
  7. 2025EIAD: Explainable Industrial Anomaly Detection Via Multi-Modal Large Language Modelscited by 11
  8. 2024VarAD: Lightweight High-Resolution Image Anomaly Detection via Visual Autoregressive Modelingcited by 9
  9. 2025OASIS: Online Sample Selection for Continual Visual Instruction Tuningcited by 9
  10. 2024Small Object Few-shot Segmentation for Vision-based Industrial Inspectioncited by 5
  11. 2024Industrial Language-Image Dataset (ILID): Adapting Vision Foundation Models for Industrial Settingscited by 4
  12. 2025Breaking Language Barriers in Visual Language Models via Multilingual Textual Regularizationcited by 4
13 more
  1. 2024Synth4Seg -- Learning Defect Data Synthesis for Defect Segmentation using Bi-level Optimizationcited by 3
  2. 2026Reasoning-Driven Anomaly Detection and Localization with Image-Level Supervisioncited by 3
  3. 2026Unification of Closed-Open Industrial Detection Scenarios: New Large-Scale Benchmarks,Challenges and Baselinescited by 3
  4. 2024Attention Fusion Reverse Distillation for Multi-Lighting Image Anomaly Detectioncited by 2
  5. 2025A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospectscited by 2
  6. 2025Downscaling Intelligence: Exploring Perception and Reasoning Bottlenecks in Small Multimodal Modelscited by 2
  7. 2025FedDyMem: Efficient Federated Learning with Dynamic Memory and Memory-Reduce for Unsupervised Image Anomaly Detectioncited by 1
  8. 2025Analyze-Prompt-Reason: A Collaborative Agent-Based Framework for Multi-Image Vision-Language Reasoningcited by 1
  9. 2023The Second-place Solution for CVPR VISION 23 Challenge Track 1 -- Data Effificient Defect Detectioncited by 0
  10. 2024Leveraging Foundation Model Automatic Data Augmentation Strategies and Skeletal Points for Hands Action Recognition in Industrial Assembly Linescited by 0
  11. 2024Find the Assembly Mistakes: Error Segmentation for Industrial Applicationscited by 0
  12. 2025Noise Fusion-based Distillation Learning for Anomaly Detection in Complex Industrial Environmentscited by 0
  13. 2026UniSpector: Towards Universal Open-set Defect Recognition via Spectral-Contrastive Visual Promptingcited by 0